Detecting Domain Polarity-Changes of Words in a Sentiment Lexicon

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3657–3668 August 1–6, 2021. ©2021 Association for Computational Linguistics 3657 Detecting Domain Polarity-Changes of Words in a Sentiment Lexicon Shuai Wang†∗, Guangyi Lv§, Sahisnu Mazumder‡, Bing Liu‡ ‡Department of Computer Science, University of Illinois at Chicago, USA §University of Science and Technology of China, Hefei, China †Amazon AI shuaiwanghk@gmail.com, gylv@mail.ustc.edu.cn sahisnumazumder@gmail.com, liub@uic.edu Abstract Sentiment lexicons are instrumental for senti- ment analysis. One can use a set of sentiment words provided in a sentiment lexicon and a lexicon-based classifier to perform sentiment analysis. One major issue with this approach is that many sentiment words (from the lexicon) are domain dependent. That is, they may be positive in some domains but negative in some others. We refer to this problem as domain polarity-changes of words from a sentiment lexicon. Detecting such words and correcting their sentiment for an application domain is very important. In this paper, we propose a graph-based technique to tackle this problem. Experimental results show its effectiveness on multiple datasets from different domains. 1 Introduction Sentiment words, also called opinion/polar words, are words that convey positive or negative sen- timents (Pang and Lee, 2008). Such sentiment- bearing words are usually pre-compiled as word lists in a sentiment lexicon, which is instrumen- tal as well as an important linguistic resource to sentiment analysis (Liu, 2012). So far, numerous studies about how to construct lexicons have been reported, which will be discussed in Section 2. Despite the fact that there is extensive research on lexicon construction, limited work has been done to solve the problem of identifying and han- dling sentiment words in a given/constructed lex- icon that have domain-dependent polarities. In real-life applications, there are almost always some sentiment words that express sentiments different from their default polarities provided in a general- purpose sentiment lexicon. For example, in the lexicon compiled by Hu and Liu (2004), the word “crush” is associated with a negative sentiment, but it actually shows a positive opinion in domain ∗Work done while at University of Illinois at Chicago blender because “crush” indicates that a blender works well, e.g., in the sentence “it does crush the ice!”. We call this problem domain polarity-change of a word in a sentiment lexicon. The polarity change of words plays a crucial role in sentiment classification. As we will see in the experiment section, without identifying and correct- ing such domain dependent sentiment words, the performance of sentiment classification could be much poorer. Although some researchers have stud- ied the domain-specific sentiment problem with lexicons, their focuses are quite different and their approaches are not suitable for our task. We will discuss them further in the following sections. Regarding sentiment classification, it is impor- tant to note that our work mainly aims to help lexicon-based approaches (Taboada et al., 2011). It does not directly help machine-learning (ML) or supervised learning approaches (Zhang et al., 2018) because the domain-dependent polarities of words are already reflected in the manually labeled training data. …

Content truncated to 500 words